Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    .define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shards
    -0.07
    ,default
    -0.06
    inness
    -0.06
    璀
    -0.06
    MN
    -0.06
    _aw
    -0.06
    #ab
    -0.06
    (Index
    -0.06
    _rc
    -0.06
    ’.↵↵
    -0.06
    POSITIVE LOGITS
    му
    0.07
    fulness
    0.07
    宗旨
    0.06
     XYZ
    0.06
     rhythms
    0.06
     Thompson
    0.06
    รอบ
    0.06
    Scaler
    0.06
     Ones
    0.06
    ering
    0.06
    Act Density 0.005%

    No Known Activations